Artificial intelligence meets pediatric orthopedics: A comparative analysis of ChatGPT-4o, Gemini 2.0, and Claude 3.5 in detecting supracondylar humeral fractures
Utku Murat Kalafat, Hüseyin Mutlu, Ramiz Yazıcı, Murat Genç, Bensu Bulut, Medine Akkan Öz, Ayşenur Gür, Mehmet Yortanlı · 2026
Read Artificial intelligence meets pediatric orthopedics: A comparative analysis of ChatGPT-4o, Gemini 2.0, and Claude 3.5 in detecting supracondylar humeral fractures by Utku Murat Kalafat, Hüseyin Mutlu, Ramiz Yazıcı, Murat Genç, Bensu Bulut, Medine Akkan Öz, Ayşenur Gür, Mehmet Yortanlı (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0353782.txt.
Description
Kalafat and colleagues tested three AI chat tools on children's elbow X-rays in a 2026 study. The injury studied, a break just above the elbow, is common in children and can harm nerves and blood flow if missed. Records covered three hundred children seen at a city hospital in Turkey, half with the break and half without.
Each tool saw the same images three times on different days. Answers were fairly steady for two tools and less steady for the third. Sorting breaks by severity grade worked best for one tool, yet overall skill stayed limited. The authors warn these tools are not ready to judge such breaks alone and need training built for children's bones.
Catalog record
| CREATOR | Utku Murat Kalafat, Hüseyin Mutlu, Ramiz Yazıcı, Murat Genç, Bensu Bulut, Medine Akkan Öz, Ayşenur Gür, Mehmet Yortanlı |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33846 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |